ClawHub
Back to skill

Security audit

Eastmoney Financial Search

Security checks across malware telemetry and agentic risk

Overview

The skill does what it claims by sending financial-news searches to Eastmoney, with some privacy and credential-management caveats but no evidence of hidden or malicious behavior.

Install only if you are comfortable sending financial-search queries to Eastmoney's API. Avoid confidential, regulated, or proprietary details in queries, set your own EASTMONEY_APIKEY where possible, and run the script from a directory where saving eastmoney_news_*.txt result files is acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill documents and uses a hardcoded default API key, which encourages use of a shared embedded credential and risks unintended disclosure, abuse, or quota exhaustion. Even if the key is intended for convenience, embedding credentials in distributable skill content is insecure because users may unknowingly transmit requests under a credential they do not control.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill sends user queries to an external HTTPS endpoint but does not clearly warn users that their prompts and potentially sensitive financial research queries leave the local environment. This creates a privacy and data-governance risk because operators may use the skill assuming local processing when their inputs are actually transmitted to a third party.

Missing User Warnings

Medium
Confidence
99% confidence
Finding
The code embeds a real-looking fallback API key directly in source, which exposes a credential to anyone with code access and causes silent use of that credential when the environment variable is unset. This can lead to unauthorized use, quota exhaustion, billing abuse, and accidental propagation of a secret through source control or downstream distributions.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.